General policy mapping: online continual reinforcement learning inspired on the insect brain.

Angel Yanguas-Gil Sandeep Madireddy

Published in: CoRR (2022)

Keyphrases

reinforcement learning
optimal policy
special case
real time
action selection
machine learning
function approximation
actor critic
action space
optimal control
swarm intelligence
decision problems
computational intelligence
image registration
state space
dynamic programming
website
learning algorithm